Feature Space Research Articles

Plant pathology identification using local-global feature level based on transformer

Deep learning plays a crucial role in addressing the challenge of plant disease identification in the field of agriculture. Detecting diseases in plants requires extensive effort, along with a comprehensive understanding of various plant diseases and increased processing time. Balancing both speed and accuracy in predicting leaf diseases in plants can significantly improve crop production and reduce environmental damage. In this paper, we examined deseases on popular plants in agriculture. We proposed a novel model to predict crop pathology on a feature space of global-local based on transformer aggregation. Paticular, we use refined feature of different layer to correlate semantics from high-level feature and low-level feature. Besides, to capture the extended temporal scale across the entire image, we employ a transformer to discern long-range dependencies among frames. Subsequently, the enhanced features incorporating these dependencies are inputted into a classifier for preliminary crop pathology prediction. The plant village dataset and VietNam strawberry disease (VNStr) dataset were utilized for training and disease classification in the experiments. Extensive experiments show that the proposed method outperforms by 99.18% and 94.05% accuracy in plant village and VNStr, respectivly. The model after being judged was applied on Android devices and therefore is easy to use.

Negation handling for sentiment analysis task: approaches and performance analysis

Negation plays an essential role in sentiment analysis within natural language processing (NLP). Its integration involves two key aspects: identifying the scope of negation and incorporating this information into the sentiment model. Before delving into scope detection, the specific negation cue must be identified, with explicit and implicit negation cues being the two main types. Various methodologies, such as rule-based, machine learning, and hybrid approaches, address the negation scope detection challenge. Strategies for leveraging negation information in sentiment models encompass heuristic polarity modification, feature space augmentation, end-to-end approach, and hierarchical multi-task learning. Notably, there is a need for more studies addressing implicit negation cue detection, even within the state-of-the-art bidirectional encoder representation for transformers (BERT) approach. Some studies have employed reinforcement learning and hybrid techniques to address the implicit negation problem. Further exploration, particularly through a hybrid and multi-task learning approach, is warranted to make potential contributions to the nuanced challenges of handling negation in sentiment analysis, especially in complex sentence structures.

A genetic algorithm-based feature selection approach for diabetes prediction

<p>Genetic algorithms have emerged as a powerful optimization technique for feature selection due to their ability to search through a vast feature space efficiently. This study discusses the importance of feature selection for prediction in healthcare and prominently focuses on diabetes mellitus. Feature selection is essential for improving the performance of prediction models, by finding significant features and removing unnecessary among them. The study aims to identify the most informative subset of features. Diabetes is a chronic metabolic disorder that poses significant health challenges worldwide. For the experiment, two datasets related to diabetes were downloaded from Kaggle and the results of both (datasets) with and without feature selection using the genetic algorithm were compared. Machine learning classifiers and genetic algorithms were combined to increase the precision of diabetes risk prediction. In the preprocessing phase, feature selection, machine learning classifiers, and performance metrics methods were applied to make this study feasible. The results of the experiment showed that genetic algorithm + logistic regression i.e., 80% (accuracy) works better for PIMA diabetes, and for Germany diabetes dataset genetic algorithm + random forest and genetic algorithm + K-Nearest Neighbor i.e., 98.5% performed better than other chosen classifiers. The researchers can better comprehend the importance of feature selection in healthcare through this study.</p>

Deepfake Video Detection Using Res-Next CNN and LSTM

Abstract: Deepfake videos are becoming more and more common in the digital age, which has led to major worries about how they can undermine the trustworthiness of visual media. With deep learning algorithms' rising processing power, producing lifelike human-synthesized films or deepfakes has never been easier. Disinformation and political unrest can be caused by these videos. A novel deep learning-based method has been created to distinguish between actual and AI-generated fraudulent videos to address this problem. The suggested technique uses Attention-based networks (Res-Next CNN), a kind of deep learning architecture that can selectively focus on significant features in a video, to fine-tune the transformer module to search for new sets of feature space to detect false images.

Subject review: Human activity recognition based on depth images

Human activity recognition (HAR) has becomes a well-known area of study for researchers due to its multiple possible applications. HAR systems are applied in many areas including supervisory nursing care, medical supervision, surveillance, human- machine interaction, gaming and entertainment, etc. However, developing a robust HAR system that incorporates a comprehensive and scalable set of feature spaces is a challenging task. Much research has been done in this area to develop efficient HAR systems. In this article, a review of the developments in Human Activity Recognition (HAR) will be presented. Human activity recognition works on two basic principles; feature extraction from sensor data and classification of features into action classes. The review presented in this article is hence divided into two parts. The first part deals with feature representation in HAR systems such as Space-time Features, Frequency Features, Local Descriptors, Optical Flow Based, and Skeleton Joints. The second part deals with the classification approaches used in the literature such as Bayesian, and HMM.

Using autoencoders and deep transfer learning to determine the stellar parameters of 286 CARMENES M dwarfs

Deep learning (DL) techniques are a promising approach among the set of methods used in the ever-challenging determination of stellar parameters in M dwarfs. In this context, transfer learning could play an important role in mitigating uncertainties in the results due to the synthetic gap (i.e. difference in feature distributions between observed and synthetic data). We propose a feature-based deep transfer learning (DTL) approach based on autoencoders to determine stellar parameters from high-resolution spectra. Using this methodology, we provide new estimations for the effective temperature, surface gravity, metallicity, and projected rotational velocity for 286 M dwarfs observed by the CARMENES survey. Using autoencoder architectures, we projected synthetic PHOENIX-ACES spectra and observed CARMENES spectra onto a new feature space of lower dimensionality in which the differences between the two domains are reduced. We used this low-dimensional new feature space as input for a convolutional neural network to obtain the stellar parameter determinations. We performed an extensive analysis of our estimated stellar parameters, ranging from 3050 to 4300\,K, 4.7 to 5.1\,dex, and $-$0.53 to 0.25\,dex for eff $, log g and Fe/H respectively. Our results are broadly consistent with those of recent studies using CARMENES data, with a systematic deviation in our $T_ eff $ scale towards hotter values for estimations above 3\,750\,K. Furthermore, our methodology mitigates the deviations in metallicity found in previous DL techniques due to the synthetic gap. We consolidated a DTL-based methodology to determine stellar parameters in M dwarfs from synthetic spectra, with no need for high-quality measurements involved in the knowledge transfer. These results suggest the great potential of DTL to mitigate the differences in feature distributions between the observations and the PHOENIX-ACES spectra.

A novel hybrid model for lung and colon cancer detection using pre-trained deep learning and KELM

Cancer poses a significant threat to life due to its aggressive nature, high potential for metastasis, and heterogeneity. Globally, both the men and women are mostly affected by lung and colon (LC) cancer. Early and accurate detection is essential to enhance the well-being of patients facing LC cancer. The traditional techniques face challenges such as low accuracy and high execution time. This work combines the pre-trained deep learning (DL) models like ResNet-50, InceptionV3, and DenseNet with Kernel Extreme Learning Machine (KELM) for the accurate and fast diagnosis of LC cancer using histopathology images. The pre-trained DL models provide a strong foundation for feature extraction, capturing intricate patterns indicative of cancerous tissues. Feature fusion combines the complementary strengths of multiple pre-trained models, enhancing the method's ability to capture diverse features and improve classification accuracy. KELM efficiently handles the high-dimensional feature space generated by the DL models, ensuring fast and accurate classification. Mutation Boosted Dwarf Mongoose Optimization Algorithm (MB-DMOA) further optimizes the model parameters, mitigating the risk of getting stuck in local optima and facilitating better convergence towards the global optimum. By leveraging the advantages of each technique and integrating them into a cohesive framework, the proposed approach achieves superior performance in diagnosing LC cancer, ultimately improving patient outcomes. The proposed study attains accuracy (98.9%), F1-score (97.6%), specificity (96.5%), precision (96.7%) and sensitivity (95.8%). The results illuminate the efficacy of this approach within therapeutic environments.

Effect of shade on simultaneous estimation of non-photosynthetic and photosynthetic vegetation cover using the NDVI-NSSI normalized difference triangular space

ABSTRACT The non-photosynthetic vegetation – soil separation index (NSSI) and normalized difference vegetation index (NDVI) can be used to simultaneously estimate the fractional cover of non-photosynthetic vegetation (fNPV), photosynthetic vegetation (fPV), and bare soil (fBS) in vegetation ecosystems. However, these estimates suffer from problems due to shading by dense vegetation or topography. Based on field-measured data and on hyperspectral data acquired by unmanned aerial vehicles, we analyse how shading affects the morphology of NDVI-NSSI and enhanced vegetation index – NSSI (EVI-NSSI). We also investigate the simultaneous estimation of fNPV, fPV, and fBS. The results show that the NDVI-NSSI normalized difference feature space mitigates the impact of shade. Shade causes the NDVI-NSSI and EVI-NSSI to shift rightward parallel to the BS axis and leftward parallel to the PV axis, respectively. Although such shifts may hinder the determination of NPV, PV, and BS endmembers, they do not affect the spectral separation of NPV. Overall, with the NDVI-NSSI and EVI-NSSI methods, the estimation error for fNPV under shaded conditions is approximately 5% greater than that under illuminated conditions. Shaded green vegetation more strongly affects the estimation error of fPV and fBS in EVI-NSSI than in NDVI-NSSI, whereas fBS and fPV depend more strongly on shade than fNPV.

Metrics for Domain Shift Characterization: Comparisons and New Directions

Domain adaptation is an important area of research, as it aims to remedy the effects of the domain shift due to differences in the distribution between the source domain used for training and the target domain where prediction takes place. However, methods for characterizing the domain shift across datasets are lacking. In this work, we propose a domain shift metric called SpOT, which stands for spherical optimal transport, by operating on the spherical manifold. We realize our approach with a spherical network, used to obtain features, and an orthogonal projection loss, used to impose orthogonality in the feature space. The resulting spherical features have better inter-class separation and lower intra-class variation compared to features in Euclidean space. This type of feature clustering makes each domain representation more compact and more suitable for further analysis. The domain shift between the datasets is calculated using the optimal transport on the spherical features, which has a sound theoretical basis. Our results are further supported by experiments that show the correlation of SpOT with a new gain of transfer measure across domain adaptation datasets.

A New Large-Scale Monitoring Index of Desertification Based on Kernel Normalized Difference Vegetation Index and Feature Space Model

As a new vegetation monitoring index, the KNDVI has certain advantages in characterizing the evolutionary process of regional desertification. However, there are few reports on desertification monitoring based on KNDVI and feature space models. In this study, seven feature parameters, including the kernel normalized difference vegetation index (KNDVI) and Albedo, were introduced to construct different models for desertification remote-sensing monitoring. The optimal desertification remote-sensing monitoring index model was determined with the measured data; then, the spatiotemporal evolution pattern of desertification in Gulang County from 2013 to 2023 was analyzed and revealed. The main conclusions were as follows: (1) Compared with the NDVI and MSAVI, the KNDVI showed more advantages in the characterization of the desertification evolution process. (2) The point–line pattern KNDVI-Albedo remote-sensing index model had the highest monitoring accuracy, reaching 94.93%, while the point–line pattern NDVI-TGSI remote-sensing monitoring index had the lowest accuracy of 54.38%. (3) From 2013 to 2023, the overall desertification situation in Gulang County showed a trend of improvement with a pattern of “firstly aggravation and then alleviation.” Additionally, the gravity center of desertification in Gulang County first shifted to the southeast and then to the northeast, indicating that the northeast’s aggravating rate of desertification was higher than in the southwest during the period. (4) From 2013 to 2023, the area of stable desertification in Gulang County was the largest, followed by the slightly weakened zone, and the most significant transition area was that of extreme desertification to severe desertification. The research results provide important decision support for the precise monitoring and governance of regional desertification.

Deep radial basis function networks with subcategorization for mitosis detection in breast histopathology images

Due to the intra-class diversity of mitotic cells and the morphological overlap with similarly looking imposters, automatic mitosis detection in histopathology slides is still a challenging task. In this paper, we propose a novel mitosis detection model in a weakly supervised way, which consists of a candidate proposal network and a verification network. The candidate proposal network based on patch learning aims to separate both mitotic cells and their mimics from the background as candidate objects, which substantially reduces missed detections in the screening process of candidates. These obtained candidate results are then fed into the verification network for mitosis refinement. The verification network adopts an RBF-based subcategorization scheme to deal with the problems of high intra-class variability of mitosis and the mimics with similar appearance. We utilize the RBF centers to define subcategories containing mitotic cells with similar properties and capture representative RBF center locations through joint training of classification and clustering. Due to the lower intra-class variation within a subcategory, the localized feature space at subcategory level can better characterize a certain type of mitotic figures and can provide a better similarity measurement for distinguishing mitotic cells from nonmitotic cells. Our experiments manifest that this subcategorization scheme helps improve the performance of mitosis detection and achieves state-of-the-art results on the publicly available mitosis datasets using only weak labels.

Enhancing Fault Identification, Classification and Location Accuracy in Transmission Lines

This research paper presents a proposed system for fault identification, classification and location in transmission lines using a Support Vector Machine (SVM)-based technique in conjunction with a Positive Sequence Analyzer. The objective is to develop an accurate and reliable method for identifying, classifying and locating different fault types in transmission lines. The proposed system leverages the capabilities of SVMs in handling high-dimensional feature spaces and the fault signature extraction capabilities of the Positive Sequence Analyzer. Experimental evaluations are conducted to assess the performance and effectiveness of the proposed system, comparing it with existing fault identification and classification methods. The results demonstrate the superior performance and robustness of the SVM-based technique utilizing the Positive Sequence Analyzer, providing a valuable contribution to fault management and system reliability in transmission line networks.

A dual fusion recognition model for sleep posture based on air mattress pressure detection

In order to solve the difficult portability problem of traditional non-invasive sleeping posture recognition algorithms arising from the production cost and computational cost, this paper proposes a sleeping posture recognition model focusing on human body structural feature extraction and integration of feature space and algorithms based on a specific air-spring mattress structure, called SPR-DE (SPR-DE is the Sleep Posture Recognition-Data Ensemble acronym form). The model combines SMR (SMR stands for Principle of Spearman Maximal Relevance) with horizontal and vertical division based on the barometric pressure signals in the human body’s backbone region to reconstruct the raw pressure data into strongly correlated non-image features of the sleep postures in different parts and directions and construct the feature set. Finally, the recognit-ion of the two sleep postures is accomplished using the AdaBoost-SVM integrated classifier. SPR-DE is compared with the base and integrated classifiers to verify its performance. The experimental results show that the amount of significant features helps the algorithm to classify different sleeping patterns more accurately, and the f1 score of the SPR-DE model determined by the comparison experiments is 0.998, and the accuracy can reach 99.9%. Compared with other models, the accuracy is improved by 2.9% ~ 7.7%, and the f1-score is improved by 0.029 ~ 0.076. Therefore, it is concluded that the SMR feature extraction strategy in the SPR-DE model and the AdaBoost-SVM can achieve high accuracy and strong robustness in the task of sleep posture recognition in a small area, low-density air-pressure mattress, taking into account the comfort of the mattress structural design and the sleep posture recognition, integrated with the mattress adaptive adjustment system.

The speech neuroprosthesis.

Loss of speech after paralysis is devastating, but circumventing motor-pathway injury by directly decoding speech from intact cortical activity has the potential to restore naturalcommunication and self-expression. Recent discoveries have defined how key features of speech production are facilitated by the coordinated activity of vocal-tract articulatory and motor-planning cortical representations. In this Review, we highlight such progress and how it has led to successful speech decoding, first in individuals implanted with intracranial electrodes for clinicalepilepsy monitoringand subsequently in individuals with paralysis as part ofearlyfeasibility clinical trials to restore speech. We discuss high-spatiotemporal-resolution neural interfaces and the adaptation of state-of-the-art speech computational algorithms that have driven rapidandsubstantial progress indecoding neural activity into text, audible speech, and facial movements. Although restoring natural speech is a long-term goal, speech neuroprostheses already have performance levels that surpass communication rates offered by current assistive-communication technology. Given this accelerated rate of progress in the field, we propose key evaluation metrics for speed and accuracy, among others, to help standardize across studies. We finish by highlighting several directions to more fully explore the multidimensional feature space of speech and language, which will continue to accelerate progress towards a clinically viable speech neuroprosthesis.

Cross-tokamak disruption prediction based on domain adaptation

The high acquisition cost and the significant demand for disruptive discharges for data-driven disruption prediction models in future tokamaks pose an inherent contradiction in disruption prediction research. In this paper, we demonstrated a novel approach to predict disruption in a future tokamak using only a few discharges based on domain adaptation (DA). The approach aims to predict disruption by finding a feature space that is universal to all tokamaks. The first step is to use the existing understanding of physics to extract physics-guided features from the diagnostic signals of each tokamak, called physics-guided feature extraction (PGFE). The second step is to align a few data from the future tokamak (target domain) and a large amount of data from existing tokamaks (source domain) based on a DA algorithm called CORrelation ALignment (CORAL). It is the first attempt at applying DA in the cross-tokamak disruption prediction task. PGFE has been successfully applied in J-TEXT to predict disruption with excellent performance. PGFE can also reduce the data volume requirements due to extracting the less device-specific features, thereby establishing a solid foundation for cross-tokamak disruption prediction. We have further improved CORAL called supervised CORAL (S-CORAL) to enhance its appropriateness in feature alignment for the disruption prediction task. To simulate the existing and future tokamak case, we selected J-TEXT as the existing tokamak and EAST as the future tokamak, which has a large gap in the ranges of plasma parameters. The utilization of the S-CORAL improves the disruption prediction performance on future tokamak. Through interpretable analysis, we discovered that the learned knowledge of the disruption prediction model through this approach exhibits more similarities to the model trained on large data volumes of future tokamak. This approach provides a light, interpretable and few data-required ways by aligning features to predict disruption using small data volume from the future tokamak.

Fine-grained recognition of bitter gourd maturity based on Improved YOLOv5-seg model

Bitter gourd, being perishable, requires timely harvesting. Delayed harvesting can result in a substantial reduction in fruit quality. while premature harvesting leads to underdeveloped fruit and decreased yields, the continuous flowering pattern in bitter gourd underscores the significance of accurately assessing fruit growth and ensuring timely harvesting for subsequent fruit setting and development. The current reliance on the experience of production personnel represents a substantial inefficiency. We present an improved real-time instance segmentation model based on YOLOv5-seg. The utilization of dynamic snake convolution enables the extraction of morphological features from the curved and elongated structure of bitter gourd. Diverse branch blocks enhance feature space diversity without inflating model size and inference time, contributing to improved recognition of expansion stages during bitter gourd growth. Additionally, the introduction of Focal-EIOU loss accurately locates the boundary box and mask, addressing sample imbalances in the L2 stage. Experimental results showcase remarkable accuracy rates of 99.3%, 93.8%, and 98.3% for L1, L2, and L3 stages using mAP@0.5. In comparison, our model outperforms other case segmentation models, excelling in both detection accuracy and inference speed. The improved YOLOv5-seg model demonstrates strong performance in fine-grained recognition of bitter gourd during the expansion stage. It efficiently segments bitter gourd in real-time under varying lighting and occlusion conditions, providing crucial maturity information. This model offers reliable insights for agricultural workers, facilitating precise harvesting decisions.

Exploration of materials fatigue influence factors using interpretable machine learning

AbstractData‐driven fatigue strength predictions are gaining popularity. Nevertheless, many machine learning models lack trustworthiness due to their limited decision‐making transparency which often hinders their practical application. In this investigation, we assess the expressiveness of the model‐agnostic explainable AI method known as SHapley Additive exPlanations (SHAP) for data‐driven fatigue strength prediction. Our study demonstrates that the SHAP feature sensitivity analysis underpins known physical relations from materials processing and fatigue theory. This even applies in view of the high‐dimensional, cross‐correlated fatigue feature space and despite data heterogeneity (different steels, component designs, and loads). For instance, SHAP indicates a fatigue strength increase with higher solid solution‐strengthening element concentrations, such as chromium and nickel. SHAP identifies correlations rather than causality. Thus, data science and domain knowledge should be closely linked during the SHAP assessment. If this is satisfied, plausible causal relations can be inferred, and spurious ones arising from confounding variables can be discarded.

Entropy pelican optimization algorithm (epoa) based feature selection and deep autoencoder (dae) of heart failure status prediction

Introduction: Heart Failure (HF) is a complicated condition as well as a significant public health issue. Data processing is now required for machine and statistical learning techniques while it helps to identify key features and eliminates unimportant, redundant, or noisy characteristics, hence minimizing the feature space's dimensions. A common cause of mortality in cases of heart disease is Dilated Cardiomyopathy (DCM). Methods: The feature selection in this work depends on the Entropy Pelican Optimization Algorithm (EPOA). It is a recreation of pelicans' typical hunting behaviour. This is comparable to certain characteristics that lead to better approaches for solving high-dimensional datasets. Then Deep Autoencoder (DAE) classifier has been introduced for the prediction of patients. DAE classifier is employed to compute the system's nonlinear function through data from the normal and failure state. Results: DAE was discovered to not only considerably increase accuracy but also to be beneficial when there is a limited amount of labelled data.Performance metrics like recall, precision, accuracy, f-measure, and error rate has been used for results analysis. Conclusion: Publicly available benchmark dataset has been collected from Gene Expression Omnibus (GEO) repository to evaluate and contrast the suitability of the suggested classifier with other existing methods.

A Time-Frequency Domain Feature Extraction Approach Enhanced by Computer Vision for Wire Arc Additive Manufacturing Monitoring Using Fourier and Wavelet Transform

Wire arc additive manufacturing (WAAM) is a rapidly growing technology that offers several advantages over traditional manufacturing methods, such as high deposition rates and the ability to build large components in a cost-effective manner. However, WAAM is also prone to the generation of defects, so the timely identification of anomalies is important to reduce the waste and get components of high quality. To develop anomaly detection application, the feature extraction process represents a key ingredient which allows machine learning systems to analyze big data. Waveform GMAW welding processes are typically used in WAAM to reduce the heat input supplied to the material and avoid defects such as excessive bending of parts and residual stress. These processes are based on the controlled dip transfer principle, so the waveforms should repeat themselves during deposition. This suggests that the frequency content of the voltage and current welding signals acquired during the process can provide important information about the process state. In this research, an experimental campaign was conducted to collect data for pulsed welding and surface tension transfer (STT) processes during the deposition of mild steel ER70S6, stainless steel 316L, Aluminum 4043, and Inconel 718 alloys. Welding voltage and current signals were acquired during the building processes, and a frequency domain analysis was conducted using the Fast Fourier transform (FFT) and discrete wavelet transform (DWT) with the aim to extract features from signals aiming to better separate the feature space, which means improve anomaly detection performance in detecting defects like arc instability, porosity, geometrical defect due to arc blow and humping. Furthermore, a methodology based on time-frequency analysis enhanced by Gabor filter for texture anomaly detection of scalograms obtained by Morlet Continuous Wavelet Transform is proposed, which showed an improvement of performance in separation between normal and anomalous deposition of several materials under different welding technologies.

Time dimension feature extraction and classification of high-dimensional large data streams based on unsupervised learning

In order to solve the problem of low accuracy of time dimension feature extraction and classification of high-dimensional large data streams, this paper proposes a time dimension feature extraction and classification algorithm of high-dimensional large data streams based on unsupervised learning. Analyze the trend of high-dimensional data flow changes under machine learning, and achieve dimensionality reduction of high-dimensional large traffic time dimensional data through local save projection. Analyze the spatial relationship between feature attributes and feature space, segment and fit high-dimensional big data streams and time dimensional feature data streams, further segment time dimensional sequences using sliding windows, and complete feature extraction through discrete dyadic wavelet transform. According to the clustering algorithm, cluster the time dimension feature data stream, calculate the cosine similarity of the feature data, model the time dimension feature stream of training samples, use the feature classification function to minimize the classification loss, and use unsupervised learning to achieve the final classification task. The test results show that this method can improve the temporal feature extraction and classification accuracy streams.